jtbd-analyze

Extract Jobs-To-Be-Done records from markdown documentation into JSONL and CSV.

Updated Aug 27, 2026

Search Tags:#content strategy #product management #user research #documentation analysis #jtbd #job statements

Ready to run

npx skills add https://github.com/redhat-documentation/redhat-docs-agent-tools --skill jtbd-analyze

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: jtbd-analyze
Source: https://github.com/redhat-documentation/redhat-docs-agent-tools/tree/main/plugins/jtbd-tools/skills/jtbd-analyze
Command: npx skills add https://github.com/redhat-documentation/redhat-docs-agent-tools --skill jtbd-analyze

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of Jobs-To-Be-Done (JTBD) from technical documentation, transforming user goals and motivations buried in text into structured, actionable insights.

Core Features & Use Cases

JTBD Extraction: Identifies and structures job statements, user stories, and related outcomes based on a defined methodology.
Scalable Processing: Handles both small and large documents efficiently, using chunked subagent processing for extensive content.
Use Case: Analyze a large product manual to identify the core jobs users are trying to accomplish, enabling content restructuring and feature prioritization aligned with user needs.

Quick Start

Use the jtbd-analyze skill to analyze the document located at docs_raw/rhoai/creating-a-workbench.md.

Frequently Asked Questions about jtbd-analyze

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract Jobs-To-Be-Done from technical documentation?▼

To extract Jobs-To-Be-Done from technical documentation, you can parse markdown content using a defined methodology to identify and structure user motivations into actionable job statements, outputting the results as structured JSONL and CSV files.

What is the best way to analyze large product manuals for user stories and outcomes?▼

Analyzing large product manuals for user stories is best handled via chunked subagent processing, which scales the extraction of job statements and outcomes efficiently without overwhelming the processing pipeline.

Can I configure the user research analysis for a specific domain?▼

Yes, you can configure user research analysis for a specific domain by applying research configuration overlays, which tailor the Jobs-To-Be-Done extraction to your domain-specific requirements.

What file formats does the JTBD extraction output for content strategy analysis?▼

The JTBD extraction outputs structured JSONL and CSV files, providing structured content strategy analysis data that can be easily integrated into downstream product management workflows.

Do I need markdown files to identify user goals and motivations in documentation?▼

Yes, you need markdown files as the input source to identify user goals and motivations, because the parsing methodology specifically reads markdown content to extract structured job statements.

Why use automated job statement extraction for product management research?▼

Automated job statement extraction transforms user goals buried in text into structured, actionable insights, enabling product management to align feature prioritization and content restructuring directly with user needs.